DeepSeek V4.1 Flash 1017 vs Kimi K3
API pricing, context, and independently measured performance, side by side. DeepSeek V4.1 Flash 1017 starts 71% cheaper on input than Kimi K3 at list prices.
DeepSeek V4.1 Flash 1017
DeepSeek · released Oct 17, 2026
Best input$0.07 / MTok
Best output$0.15 / MTok
Context1.05M
Providers28
Fastest measured0.69s° TTFT · 131 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Kimi K3
Moonshot AI · released Jul 16, 2026
Best input$0.238 / MTok
Best output$5.50 / MTok
Context1.05M
Providers30
Fastest measured0.8s° TTFT · 105 tok/s
Open weightsVisionToolsReasoningStructured outputPrompt caching
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | OPOpenInference | $0.07 | $0.50 | — | — | — |
| DeepSeek V4.1 Flash 1017 |  Relace | $0.07 | $0.50 | 0.69s° | 131° tok/s | — |
| DeepSeek V4.1 Flash 1017 |  InferenceNet | $0.08 | $0.50 | — | — | — |
| Kimi K3 |  Wafer | $0.238 | $24.00 | 1.7s° | 117° tok/s | 0/5 |
| Kimi K3 | InferenceNet | $0.239 | $11.94 | — | — | — |
| Kimi K3 | Relace | $0.30 | $12.00 | 2.6s° | 113° tok/s | — |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) · chat10k profile (~10K in / 200 out) · ° = measured via OpenRouter routing (adds a hop) · SMOKE: of 5 programmatic capability probes passed · methodology v1.1 — full details on each model page